© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 144280
    Prev
    Next
    INDEX
    Explanations

    code review aiming for improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    1.24
    '
    0.99
    <
    0.96
    ;
    0.89
    )
    0.88
    {
    0.86
    ).
    0.86
    *
    0.86
    (
    0.85
    !
    0.84
    POSITIVE LOGITS
     سایټ
    0.78
     بي
    0.72
     は
    0.70
    ្សែ
    0.70
     세포
    0.70
     または
    0.70
     于
    0.70
     ಹೇಳ
    0.68
     კ
    0.67
     会
    0.67
    Activations Density 0.000%

    No Known Activations